library(tidyverse)
library(tidytext)
library(DT)
library(scales)
library(wordcloud2)
library(gridExtra)
library(ngram)
library(shiny)
We use the processed data for our analysis and combine it with the demographic information available.
hm_data <- read_csv("../output/processed_moments.csv")
urlfile<-'https://raw.githubusercontent.com/rit-public/HappyDB/master/happydb/data/demographic.csv'
demo_data <- read_csv(urlfile)
hm_data <- hm_data %>%
inner_join(demo_data, by = "wid") %>%
select(wid,
original_hm,
gender,
marital,
parenthood,
reflection_period,
age,
country,
ground_truth_category,
text) %>%
mutate(count = sapply(hm_data$text, wordcount)) %>%
filter(gender %in% c("m", "f")) %>%
filter(marital %in% c("single", "married")) %>%
filter(parenthood %in% c("n", "y")) %>%
filter(reflection_period %in% c("24h", "3m")) %>%
mutate(reflection_period = fct_recode(reflection_period,
months_3 = "3m", hours_24 = "24h"))
datatable(hm_data)
## Warning in instance$preRenderHook(instance): It seems your data is too
## big for client-side DataTables. You may consider server-side processing:
## https://rstudio.github.io/DT/server.html